WO2018053847A1 - 一种智能库存管理系统、服务器、方法、终端和程序产品 - Google Patents
一种智能库存管理系统、服务器、方法、终端和程序产品 Download PDFInfo
- Publication number
- WO2018053847A1 WO2018053847A1 PCT/CN2016/100132 CN2016100132W WO2018053847A1 WO 2018053847 A1 WO2018053847 A1 WO 2018053847A1 CN 2016100132 W CN2016100132 W CN 2016100132W WO 2018053847 A1 WO2018053847 A1 WO 2018053847A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- item
- machine terminal
- server
- image
- smart machine
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
Definitions
- the present invention relates to the field of cloud robot technology, and in particular, to an intelligent inventory management system, a server, a method, a terminal, and a program product.
- the cloud robot is a smart machine terminal that puts the cognitive system in the cloud, the body, the drive and the sensor are placed on the robot body, and the two are connected by mobile communication; the cloud robot is the development direction of the intelligent humanoid robot.
- the embodiment of the present application proposes an intelligent inventory management system, a server, a method, a terminal, and a program product, which are used to reduce the complexity of inventory management.
- an embodiment of the present application provides an intelligent inventory management server, including an object recognition module and an inventory management module, where:
- the object recognition module is configured to determine an item and a quantity in the image according to image recognition captured by the smart machine terminal;
- the inventory management module is configured to store the item and the inventory information identified by the object recognition module into a warehouse.
- an embodiment of the present application provides an intelligent inventory management system, including the smart inventory management server provided by the first aspect, and an intelligent machine terminal:
- the intelligent machine terminal is configured to photograph an item and send the captured image to the server.
- an embodiment of the present application provides an intelligent machine terminal, including a camera, a second communication component, and a second processor component, where:
- the camera is used for photographing an item
- the second processor component is configured to capture an image of an item in the warehouse by the camera and transmit the captured image to the smart inventory management server via the second communication component.
- an embodiment of the present application provides a smart inventory management method, including:
- the intelligent machine terminal captures the item and sends the captured image to the smart inventory management server;
- the smart inventory management server receives an image captured by the smart machine terminal, determines an item and a stock in the image by image recognition captured by the smart machine terminal, and saves the information to the inventory information.
- an embodiment of the present application provides a computer program product for intelligent inventory management, the computer program product comprising a computer readable storage medium and a computer program mechanism embedded therein, the computer program mechanism comprising Instructions for performing the various steps in the method of the fourth aspect.
- an embodiment of the present application provides an intelligent inventory management server, including a first communication component, a first processor component, and a memory component, wherein:
- the first communication component is configured to receive an image captured by the smart machine terminal
- the memory component is configured to store inventory information
- the first processor component is configured to determine an item and a quantity in the image by image recognition captured by the smart machine terminal and save to the memory component.
- the smart machine terminal captures an item, and sends the captured image to the smart inventory management server; the smart inventory management server identifies the item in the image according to the image captured by the smart machine terminal and Stock; store the item and stock information.
- the embodiment of the present application utilizes the item identification technology to identify the item by taking a picture of the item, and automatically input the item information into the inventory information base.
- the embodiment of the present application does not need to be manually entered, which avoids the problem that the manual entry of the item list is easy to cause registration errors due to human negligence; it is also unnecessary to implant any object in the item in advance, which makes the process flow more convenient.
- FIG. 1 is a schematic structural diagram of a smart inventory management system according to an embodiment of the present application.
- FIG. 2 is a schematic flowchart of a smart inventory management method in an embodiment of the present application
- FIG. 3 is a schematic flowchart of a smart inventory management method according to Embodiment 1 of the present application.
- FIG. 4 is a schematic flowchart of a smart inventory management method according to Embodiment 2 of the present application.
- FIG. 5 is a schematic flowchart of a method for inspecting an inventory of an intelligent machine terminal according to Embodiment 3 of the present application;
- FIG. 6 is a schematic structural diagram of an intelligent machine terminal according to an embodiment of the present application.
- FIG. 7 is a schematic structural diagram of a smart inventory management server in an embodiment of the present application.
- FIG. 8 is another schematic structural diagram of a smart inventory management server in an embodiment of the present application.
- the smart inventory management server 104 includes an object identification module 102 and an inventory management module 103. :
- the smart machine terminal 101 is configured to photograph an item, and send the captured image to the object recognition module 102;
- the object recognition module 102 is configured to identify an item and a stock in the image according to an image captured by the smart machine terminal 101;
- the inventory management module 103 is configured to store the items and the inventory information identified by the object recognition module 102.
- the object identification module 102 and the inventory management module 103 may be arranged in different physical servers, or may be arranged in the same physical server.
- FIG. 2 shows a smart inventory management method in the embodiment of the present application, as shown in the figure, including:
- Step 201 the smart machine terminal 101 takes an item and sends the captured image to the object recognition module 102 of the smart inventory management server 104;
- Step 202 The object recognition module 102 identifies an item and a stock in the image according to an image captured by the smart machine terminal 101.
- step 203 the inventory management module 103 of the smart inventory management server 104 stores the items and inventory information identified by the object recognition module 102.
- the object recognition technology can be used to quickly and accurately identify an item, and through the training of a large amount of item data, the item information can be automatically recorded into the inventory system, and the actual image information of the item can also be Entry into the inventory management system reduces the amount of manual entry, provides accuracy in the storage of item information, and reduces the cost of implanting RFID, QR code, barcode sensing components, and IoT chips for items.
- the proposal for object entry using object recognition technology mentioned in the proposal can be used for inventory in various industries. management.
- the inventory management module 103 can also store the image together with the item information into the object.
- This operation completes the image information of the item and ensures an accurate one-to-one correspondence with the item.
- the integrity of the item information is improved, and the data entered in the prior art discovered by the inventors cannot contain the item image information.
- the object recognition module 102 can also send feedback information of whether the item identification is successful to the smart machine terminal 101;
- the smart machine terminal 101 can also perform the next item shooting when the feedback information is successful for recognition; and retake the item from another angle when the feedback information is that the recognition fails.
- This processing can increase the fault tolerance performance of the item identification. If the identification cannot be successful once, the intelligent inventory management system itself can re-identify, thereby increasing the possibility of successful recognition. Of course, in order to avoid the process of infinite loop that can not be recognized successfully, you can set the number of re-recognition. If the recognition is still not successful, the next item will be taken; or the different shooting angles of the item will be recorded. If you have tried but still can't succeed, take the next item.
- the smart machine terminal 101 can shoot an item through the camera according to a preset period; or
- the object is photographed by moving to the position specified by the object recognition module 102.
- the intelligent machine terminal 101 in the embodiment of the present application is mainly used in a warehouse management environment, and is designed as a robot that can walk freely in the warehouse, can raise and lower its own height, and can recognize an object.
- the smart machine terminal 101 can perform a patrol inspection from the first shelf of the warehouse at each inspection.
- the intelligent machine terminal 101 utilizes a combination of overall recognition and split recognition to identify The method identifies each partition of each shelf.
- the intelligent machine terminal 101 obtains the overall information of the partitioned article by overall identification, and separately identifies each item according to the interval between the articles (the dividing line between the available articles and the articles), and finally obtains Information about the item.
- the object recognition module 102 can perform object recognition using feature extraction based machine vision techniques and convolutional neural network based deep learning techniques.
- each item entry is a process of self-learning, which is used to enrich its own knowledge base and improve the accuracy of item identification.
- the object recognition module 102 can also recognize the barcode of the item in the image captured by the smart machine terminal 101, thereby completing the identification of the item in the image.
- the object identification module 102 and the inventory management module 103 are functional divisions of the smart inventory management server 104.
- the smart inventory management method in the embodiment of the present application can be understood as:
- the smart machine terminal 101 takes an item and sends the captured image to the smart inventory management server 104;
- the smart inventory management server 104 receives the image captured by the smart machine terminal 101, and identifies the item and the stock in the image by the image recognition of the smart machine terminal 101 and stores it in the inventory information.
- FIG. 3 shows the smart inventory management method in the first embodiment, as shown in the figure. Shown, including:
- Step 301 the intelligent machine terminal 101 periodically wakes up autonomously
- the intelligent machine terminal 101 periodically wakes up autonomously in order to save power when the item is not photographed.
- the step of waking up is not necessarily included, and the smart machine terminal 101 can work all the time and photograph the item through the camera according to a preset period.
- Step 302 the smart machine terminal 101 captures an item
- Step 303 the smart machine terminal 101 sends the captured image to the object recognition module 102 in the cloud;
- Step 304 The smart machine terminal 101 receives feedback information indicating whether the item identification sent by the object recognition module 102 is successful;
- Step 305 the smart machine terminal 101 determines whether the feedback information is successful, if yes, proceed to step 306, otherwise, proceed to step 307;
- Step 306 the smart machine terminal 101 performs the next item shooting
- the smart machine terminal may also be a process of determining whether to enter the next item according to the item successfully entered information sent by the inventory management module 103. That is, if the feedback information received by the smart machine terminal 101 is successful, the subsequent operation is not performed, and the inventory management module 103 sends the item successfully entered information when the entry is successful, and the smart machine terminal 101 receives the information successfully after entering the item. Then proceed to the processing of the next item.
- Step 307 the smart machine terminal 101 determines whether the number of times the same item is taken is greater than the set value N, and if so, proceeds to step 306, otherwise proceeds to step 308;
- N is a natural number and can be set as needed.
- step 308 the smart machine terminal 101 moves and retakes the item from another angle, and returns to step 304.
- FIG. 4 shows an embodiment.
- the intelligent inventory management method of the second includes:
- Step 401 The smart machine terminal 101 receives a wake-up command, where the wake-up command carries specified location information of the photographed item;
- the wake-up command received by the smart machine terminal 101 may be an identification task initiated by the cloud object recognition module 102.
- the specified location information of the photographed item is not necessarily carried in the wake-up command, and may also be sent separately.
- Step 402 the smart machine terminal 101 wakes up the smart machine terminal 101 according to the instruction and moves to the position specified by the wake-up instruction to perform object shooting;
- Step 403 the smart machine terminal 101 sends the captured image to the object recognition module 102 in the cloud;
- Step 404 The smart machine terminal 101 receives feedback information indicating whether the item identification sent by the object recognition module 102 is successful;
- Step 405 the smart machine terminal 101 determines whether the feedback information is successful, if yes, proceed to step 406, otherwise, proceed to step 407;
- Step 406 the smart machine terminal 101 performs the next item shooting
- step 407 the smart machine terminal 101 moves and retakes the item from another angle, and returns to step 404.
- the smart machine terminal 101 directly moves and re-photographs the item from another angle when the recognition is unsuccessful, which may cause an infinite loop that continues to be recognized on the same item until the recognition is unsuccessful, but In practice, the possibility of unrecognized unsuccessful is low, and setting a judgment step less can save the process. Therefore, this is also a feasible implementation.
- an intelligent machine terminal 101 inventory inspection task flow that is, intelligence is provided.
- the machine terminal 101 can perform inspection verification on the recognition result after the identification is completed.
- the method for inspecting the inventory of the intelligent machine terminal 101 of the third embodiment is as shown in FIG. 5, and includes the following steps:
- Step 501 The smart machine terminal 101 takes photos of the inventory items one by one;
- the intelligent machine terminal 101 in the method may be a timed autonomous wake-up, or may be wake-up by the network side for inventory inspection.
- Step 502 the smart machine terminal 101 sends the captured image to the object recognition module 102;
- Step 503 the object recognition module 102 performs recognition according to the received image
- step 504 the inventory management module 103 queries the item information stored in the inventory management system according to the recognition result of the object recognition module 102, and checks information such as the position, appearance, quantity, and the like of the item.
- the embodiment of the present application further provides a computer program product for intelligent inventory management, the computer program product comprising a computer readable storage medium and a computer program mechanism embedded therein, the computer program mechanism comprising Instructions for each step in the method provided.
- an intelligent machine terminal 101 is also provided in the embodiment of the present application. Since the principle of solving the problem of these devices is similar to an intelligent inventory management method, the implementation of these devices can be referred to the implementation of the method, and the repetition is performed. No longer.
- an intelligent machine terminal 101 includes a camera 601, a second communication component 602, and a second processor component 603:
- the second processor component 603 is configured to capture an image of an item in the warehouse through the camera 601, and transmit the captured image to the smart inventory management server 104 through the second communication component 602.
- the second processor component 602 is configured to capture an image of an item in the warehouse by using the camera 601, including:
- the smart machine terminal 101 When the second communication component 602 receives the wake-up command, the smart machine terminal 101 is woken up according to the command and moved to the position specified by the wake-up command for article photographing.
- the smart inventory management server 104 in the embodiment of the present application includes an object recognition module 102 and an inventory management module 103, wherein:
- the object recognition module 102 is configured to determine an item and a quantity in the image according to an image recognition captured by the smart machine terminal 10;
- the inventory management module 103 is configured to store the items and the inventory information identified by the object recognition module 102.
- the object recognition module 102 identifies the items and the stocks in the image according to the image captured by the smart machine terminal 101 by using the feature extraction based machine vision technology and the convolutional neural network based deep learning technology for object recognition.
- the inventory management module 103 also stores the image along with the item and inventory information.
- the smart inventory management server 104 further includes a first interaction module; the first interaction module is configured to display a first interface, where the first interface is used for the user to select an item that needs to view the inventory information;
- the first interaction module is further configured to: when the user selects the corresponding item through the first interface, display the picture and the stock information corresponding to the item selected by the user; and when the user modifies the displayed inventory information, The stock information corresponding to the item is updated.
- the smart inventory management server 104 further includes a second interaction module, where the first interaction module is used to display the second interface, and the second interface is used for the user to select an item that needs to view the real-time image;
- the second interaction module is further configured to: when the user selects the corresponding item through the second interface, control the smart machine terminal 101 to arrive at the location where the item is located, and upload the captured real-time image to the smart inventory management server 104; The actual received by the intelligent inventory management server 104 When the image is displayed.
- both the first interaction module and the second interaction module both can be implemented by the same interaction module.
- the smart inventory management server 104 in the embodiment of the present application may further include a first communication component 801, a first processor component 802, and a memory component 803 as shown in FIG. 8, wherein:
- a first communication component 801 configured to receive an image captured by the smart machine terminal 101
- the first processor component 802 is configured to determine an item and a stock in the image by image recognition captured by the smart machine terminal 101 and save to the memory component 803.
- determining an item and a stock in the image by image recognition captured by the smart machine terminal includes: performing object recognition using a feature extraction based machine vision technique and a convolutional neural network based deep learning technique.
- the first processor component 802 also saves the image to the memory component 803 along with the item and inventory information.
- the smart inventory management server 104 is further configured to display a first interface, where the first interface is used for the user to select an item that needs to view the inventory information;
- the smart inventory management server 104 is further configured to: when the user selects the corresponding item through the first interface, display the picture and the stock information corresponding to the item selected by the user; and when the user modifies the displayed inventory information, the item The corresponding stock information is updated.
- the smart inventory management server 104 is further configured to display a second interface, where the second interface is used for the user to select an item that needs to view the real-time image;
- the intelligent inventory management server 104 is further configured to: when the user selects the corresponding item through the second interface, control the smart machine terminal 101 to arrive at the location where the item is located and upload the captured real-time image to the smart inventory management server 104; The real-time image received by the smart inventory management server 104 is displayed.
- the smart inventory management system in the embodiment of the present application as shown in FIG. 1 may include the smart machine terminal 101 and the smart inventory management server 104 in the embodiment of the present application. Further, the object recognition module 102 is further configured to identify the item. Successful feedback information is sent to the smart machine terminal 101;
- the intelligent machine terminal 101 is further configured to retake the item from another angle when the feedback information is a recognition failure.
- the smart machine terminal 101 is configured to photograph an item, including: the intelligent machine terminal 101 periodically wakes up to perform item shooting; or
- the item identification module 102 is further configured to send a wake-up instruction to the smart machine terminal 101;
- the smart machine terminal 101 for photographing an item includes the smart machine terminal 101 performing photographing of an item according to the received wake-up instruction.
- the smart machine terminal 101 may specifically wake up and move to the position specified by the object recognition module 102 to perform object shooting according to the received wake-up instruction of the object recognition module 102.
- embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
- computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
- the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
- the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
- These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
- the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
一种智能库存管理系统、服务器、方法、终端和程序产品,属于云端机器人技术领域,用于降低库存管理的复杂程度。其中该方法包括:智能机器终端(101)拍摄物品,并将拍摄到的图像发送到智能库存管理服务器(104);所述智能库存管理服务器(104)根据所述智能机器终端(101)拍摄到的图像识别确定所述图像中的物品及存量;并将物体识别模块(102)识别出的物品及存量信息入库。利用物体识别技术,减少了人工录入的工作量,提高了物品信息入库的准确性,降低了库存管理的复杂程度。
Description
本发明涉及云端机器人技术领域,特别涉及一种智能库存管理系统、服务器、方法、终端和程序产品。
云端机器人是将认知系统放在云里,身体、驱动、传感器放在机器人本体上,通过移动通信将二者连接起来的智能机器终端;云端机器人是智能仿人机器人发展的方向。
目前的库存管理系统中的物品录入,多数为手工录入的方式,近来也有些基于物联网技术,通过识别物品中植入的RFID(Radio Frequency Identification,射频识别)、二维码、条形码传感部件及物联网芯片的方式录入,但是这样的物品录入均存在一些问题。手工录入物品清单很容易因为人为疏忽造成登记出错的问题;而通过识别物品中植入的RFID、二维码、条形码传感部件及物联网芯片的方式,需要预先在物品中植入这些传感部件及物联网芯片,使得处理流程更加复杂,并且每一次识别均需植入这些传感部件及物联网芯片也带来了成本的问题。
发明内容
本申请实施例提出了一种智能库存管理系统、服务器、方法、终端和程序产品,用于降低库存管理的复杂程度。
在第一个方面,本申请实施例提供了一种智能库存管理服务器,包括物体识别模块和库存管理模块,其中:
所述物体识别模块,用于根据智能机器终端拍摄到的图像识别确定所述图像中的物品及存量;
所述库存管理模块,用于将所述物体识别模块识别出的物品及存量信息入库。
在第二个方面,本申请实施例提供了一种智能库存管理系统,包括上述第一个方面提供的智能库存管理服务器,以及智能机器终端:
所述智能机器终端,用于拍摄物品,并将拍摄到的图像发送到所述服务器。
在第三个方面,本申请实施例提供了一种智能机器终端,包括摄像头、第二通信部件、第二处理器部件,其中:
所述摄像头,用于拍摄物品;
所述第二处理器部件用于通过所述摄像头拍摄仓库中的物品的图像,并通过所述第二通信部件将拍摄到的图像传送到智能库存管理服务器。
在第四个方面,本申请实施例提供了一种智能库存管理方法,包括:
智能机器终端拍摄物品,并将拍摄到的图像发送到智能库存管理服务器;
所述智能库存管理服务器接收所述智能机器终端拍摄到的图像,通过对所述智能机器终端拍摄到的图像识别确定所述图像中的物品及存量并保存到库存信息。
在第五个方面,本申请实施例提供了一种智能库存管理的计算机程序产品,所述计算机程序产品包括计算机可读的存储介质和内嵌于其中的计算机程序机制,所述计算机程序机制包括用于执行第四个方面所述方法中各个步骤的指令。
在第六个方面,本申请实施例提供了一种智能库存管理服务器,包括第一通信部件、第一处理器部件和存储器部件,其中:
所述第一通信部件,用于接收智能机器终端拍摄到的图像;
所述存储器部件,用于存储库存信息;
所述第一处理器部件,用于通过对智能机器终端拍摄到的图像识别确定所述图像中的物品及存量,并保存到所述存储器部件。
有益效果如下:
在本申请实施例中,智能机器终端拍摄物品,并将拍摄到的图像发送到智能库存管理服务器;所述智能库存管理服务器根据所述智能机器终端拍摄到的图像识别所述图像中的物品及存量;并将物品及存量信息入库。本申请实施例利用物品识别技术,通过对物品进行拍照,识别出该物品,将物品信息自动录入到库存信息库中。本申请实施例不需要手工录入,避免了手工录入物品清单很容易因为人为疏忽造成登记出错的问题;也无需预先在物品中植入任何物体,使得处理流程更加便捷。
下面将参照附图描述本发明的具体实施例,其中:
图1为本申请实施例中智能库存管理系统的结构示意图;
图2为本申请实施例中的智能库存管理方法流程示意图;
图3为本申请实施例一中的智能库存管理方法流程示意图;
图4为本申请实施例二中的智能库存管理方法流程示意图;
图5为本申请实施例三中的智能机器终端库存巡检方法流程示意图;
图6为本申请实施例中智能机器终端的结构示意图;
图7为本申请实施例中的智能库存管理服务器的结构示意图;
图8为本申请实施例中的智能库存管理服务器的另一个结构示意图。
为了使本发明的技术方案及优点更加清楚明白,以下结合附图对本发明的示例性实施例进行进一步详细的说明,显然,所描述的实施例仅是本发明的一部分实施例,而不是所有实施例的穷举。并且在不冲突的情况下,
本说明中的实施例及实施例中的特征可以互相结合。
图1示出了本申请实施例中的智能库存管理系统,如图所示,包括智能机器终端101和智能库存管理服务器104,智能库存管理服务器104包括物体识别模块102和库存管理模块103,其中:
智能机器终端101,用于拍摄物品,并将拍摄到的图像发送到物体识别模块102;
物体识别模块102,用于根据智能机器终端101拍摄到的图像识别该图像中的物品及存量;
库存管理模块103,用于将物体识别模块102识别出的物品及存量信息入库。
其中,物体识别模块102和库存管理模块103可以布置在不同的物理服务器中,也可以布置在同一个物理服务器中。
图2示出了本申请实施例中的智能库存管理方法,如图所示,包括:
步骤201,智能机器终端101拍摄物品,并将拍摄到的图像发送到智能库存管理服务器104的物体识别模块102;
步骤202,物体识别模块102根据智能机器终端101拍摄到的图像识别该图像中的物品及存量;
步骤203,智能库存管理服务器104的库存管理模块103将物体识别模块102识别出的物品及存量信息入库。
本申请实施例提供的智能库存管理方法中,利用物体识别技术,能够快速、准确的识别物品,通过大量物品数据的训练,可以将物品信息自动录入库存系统,同时还可以将物品的实际图像信息录入到库存管理系统中,减少了人工录入的工作量,提供了物品信息入库的准确性,也还降低了为物品植入RFID、二维码、条形码传感部件及物联网芯片的成本,该提案中提到的利用物体识别技术进行物品录入的方案,可以用于各类行业的库存
管理。
进一步地,库存管理模块103还可以将该图像与该物品信息一起入库物体。
如此操作完善了物品的图像信息,且保证与物品准确的一一对应。提升了物品信息的完整性,而发明人发现的现有技术中录入的数据都不能包含物品图像信息。
进一步地,物体识别模块102还可以将物品识别是否成功的反馈信息发送给智能机器终端101;
智能机器终端101还可以在反馈信息为识别成功时,进行下一个物品拍摄;在反馈信息为识别失败时,从另一角度重新拍摄物品。
这样处理可以增大物品识别的容错性能,若一次无法识别成功,则智能库存管理系统自身就可以进行重新识别,从而增大识别成功的可能性。当然,为了避免一直无法识别成功而导致流程死循环,可设置重新识别的次数,若多次识别仍然无法成功,则进行下一个物品拍摄;或者对该物品的不同拍摄角度进行记录,若各个角度均已尝试但仍然无法成功,则进行下一个物品拍摄。
进一步地,智能机器终端101可以按照预设周期通过摄像头拍摄物品;或者
根据接收到的所述物体识别模块102的唤醒指令,唤醒并运动到所述物体识别模块102指定的位置进行物品拍摄。
支持不同的唤醒方式,使得本申请实施例的方案更加灵活。
本申请实施例中的智能机器终端101主要用于仓储管理环境,被设计为可以在仓储中任意行走,可以升降自身高度并可以识别物体的机器人。在具体实现时,智能机器终端101可以在每次巡检时,从仓库的第一个货架开始进行巡检。智能机器终端101利用整体识别和分体识别的结合识别
方法对每一个货架的每一个隔断进行识别。智能机器终端101通过整体识别得到该隔断物品整体信息,对于堆叠在一起的物品,再根据物品之间的间隔(可利用物品与物品之间的分割线)分体识别每个物品,最终得出物品的信息。
进一步地,物体识别模块102可以利用基于特征提取的机器视觉技术和基于卷积神经网络的深度学习技术进行物体识别。
对于基于卷积神经网络深度学习的物品识别方案,每次物品录入都是自学习的一个过程,用于丰富自身知识库,提高物品识别的准确度。
在具体实现时,物体识别模块102也可以通过对智能机器终端101拍摄到的图像中物品的条形码进行识别,从而完成该图像中的物品的识别。
物体识别模块102和库存管理模块103是对智能库存管理服务器104的功能性划分,在不做具体划分时,本申请实施例中的智能库存管理方法可以理解为:
智能机器终端101拍摄物品,并将拍摄到的图像发送到智能库存管理服务器104;
智能库存管理服务器104接收智能机器终端101拍摄到的图像,通过对智能机器终端101拍摄到的图像识别确定图像中的物品及存量并保存到库存信息。
在不做具体划分时,可以理解本文描述中物体识别模块102和库存管理模块103所做的操作均是智能库存管理服务器104执行的。
为了便于更好的理解本发明,下面以实例进行说明。
实施例一
在实施例一中,从智能机器终端101的实现角度进行描述,且实施例一中由智能机器终端101主动发起物品识别任务,图3示出了实施例一中的智能库存管理方法,如图所示,包括:
步骤301,智能机器终端101定时自主唤醒;
智能机器终端101定时自主唤醒是为了在不进行物品拍摄时省电,在具体实现中,不一定包括唤醒的步骤,智能机器终端101可以一直工作,并按照预设周期通过摄像头拍摄物品。
步骤302,智能机器终端101拍摄物品;
步骤303,智能机器终端101将拍摄到的图像发送至云端的物体识别模块102;
步骤304,智能机器终端101接收物体识别模块102发送的物品识别是否成功的反馈信息;
步骤305,智能机器终端101判断该反馈信息是否为识别成功,若是,进行步骤306,否则,进行步骤307;
步骤306,智能机器终端101进行下一个物品拍摄;
在具体实现时,智能机器终端也可以是根据库存管理模块103发送的物品成功录入信息来确定是否进入下一个物品的处理。即,智能机器终端101若收到的反馈信息为成功,暂不进行后续操作,而库存管理模块103会在录入成功时发送物品成功录入信息,智能机器终端101在接收到物品成功录入信息后,再进行下一物品的处理。
步骤307,智能机器终端101判断拍摄同一物品的次数是否大于设定值N,若是,进行步骤306,否则进行步骤308;
其中N为自然数,可根据需要设置。
步骤308,智能机器终端101移动并从另一角度重新拍摄物品,返回步骤304。
实施例二
在实施例二中,从智能机器终端101的实现角度进行描述,且实施例二中智能机器终端101根据接收到的唤醒指令被唤醒,图4示出了实施例
二中的智能库存管理方法,如图所示,包括:
步骤401,智能机器终端101接收到唤醒指令,该唤醒指令中携带拍摄物品的指定位置信息;
智能机器终端101接收到的唤醒指令可以是云端物体识别模块102发起的识别任务。
在具体实现中,拍摄物品的指定位置信息不一定携带在唤醒指令中,也可以单独发送。
步骤402,智能机器终端101根据该指令唤醒智能机器终端101并运动到该唤醒指令指定的位置进行物品拍摄;
步骤403,智能机器终端101将拍摄到的图像发送至云端的物体识别模块102;
步骤404,智能机器终端101接收物体识别模块102发射的物品识别是否成功的反馈信息;
步骤405,智能机器终端101判断该反馈信息是否为识别成功,若是,进行步骤406,否则,进行步骤407;
步骤406,智能机器终端101进行下一个物品拍摄;
步骤407,智能机器终端101移动并从另一角度重新拍摄物品,返回步骤404。
可见,实施例二中,智能机器终端101在识别不成功时是直接移动并从另一角度重新拍摄物品,这样可能造成一直识别不成功而一直在同一个物品上不断识别的死循环,但是,在实践中,一直识别不成功的可能性很低,而少设置一个判断步骤,能够节省流程,因此,这也是一种可行的实现方式。
实施例三
实施例三中提供了一个智能机器终端101库存巡检任务流程,即智能
机器终端101可以在识别完成之后,再对识别结果进行检查验证。实施例三的智能机器终端101库存巡检方法如图5所示,包括如下步骤:
步骤501,智能机器终端101逐个对库存物品进行拍照;
本方法中的智能机器终端101可以是定时自主唤醒,也可由网络侧唤醒来进行库存巡检。
步骤502,智能机器终端101将拍摄到的图像发送给物体识别模块102;
步骤503,物体识别模块102根据接收到的图像进行识别;
步骤504,库存管理模块103根据物体识别模块102的识别结果查询库存管理系统中保存的物品信息,对物品的位置、外观、数量等信息进行检查。
本申请实施例还提供一种智能库存管理的计算机程序产品,该计算机程序产品包括计算机可读的存储介质和内嵌于其中的计算机程序机制,该计算机程序机制包括用于执行本申请实施例中提供的方法中各个步骤的指令。
基于同一发明构思,本申请实施例中还提供了一种智能机器终端101,由于这些设备解决问题的原理与一种智能库存管理方法相似,因此这些设备的实施可以参见方法的实施,重复之处不再赘述。
如图6所示,一种智能机器终端101,包括摄像头601、第二通信部件602、第二处理器部件603:
摄像头601,用于拍摄物品;
第二处理器部件603,用于通过摄像头601拍摄仓库中的物品的图像,并通过第二通信部件602将拍摄到的图像传送到智能库存管理服务器104。
进一步地,第二处理器部件602用于通过摄像头601拍摄仓库中的物品的图像包括:
按照预设周期通过摄像头601拍摄物品;或者
在第二通信部件602接收到唤醒指令时,根据该指令唤醒智能机器终端101并运动到该唤醒指令指定的位置进行物品拍摄。
本申请实施例中的智能库存管理服务器104如图7所示,包括物体识别模块102和库存管理模块103,其中:
物体识别模块102,用于根据智能机器终端10拍摄到的图像识别确定所述图像中的物品及存量;
库存管理模块103,用于将物体识别模块102识别出的物品及存量信息入库。
进一步地,物体识别模块102根据智能机器终端101拍摄到的图像识别该图像中的物品及存量具体为:利用基于特征提取的机器视觉技术和基于卷积神经网络的深度学习技术进行物体识别。
进一步地,库存管理模块103还将该图像与所述物品及存量信息一起入库。
进一步地,智能库存管理服务器104还包括第一交互模块;第一交互模块用于展示第一界面,第一界面用于供用户选择需要查看存量信息的物品;
所述第一交互模块还用于,在用户通过所述第一界面选择对应的物品时,展示用户所选择的物品对应的图片以及存量信息;并在用户修改所展示的存量信息时,将该物品对应的存量信息更新。
进一步地,智能库存管理服务器104还包括第二交互模块,第一交互模块用于展示第二界面,第二界面用于供用户选择需要查看实时图像的物品;
所述第二交互模块还用于,在用户通过第二界面选择对应的物品时,控制智能机器终端101到达该物品所在的位置拍摄并将拍摄到的实时图像上传到智能库存管理服务器104;并将智能库存管理服务器104接收到的实
时图像展示。
在同时具有第一交互模块和第二交互模块时,二者可以由同一交互模块实现。
本申请实施例中的智能库存管理服务器104还可以如图8所示,包括第一通信部件801、第一处理器部件802和存储器部件803,其中:
第一通信部件801,用于接收智能机器终端101拍摄到的图像;
存储器部件803,用于存储库存信息;
第一处理器部件802,用于通过对智能机器终端101拍摄到的图像识别确定所述图像中的物品及存量,并保存到存储器部件803。
进一步地,通过对智能机器终端拍摄到的图像识别确定图像中的物品及存量包括:利用基于特征提取的机器视觉技术和基于卷积神经网络的深度学习技术进行物体识别。
进一步地,第一处理器部件802还将图像与物品及存量信息一起保存到所述存储器部件803。
进一步地,智能库存管理服务器104还用于展示第一界面,第一界面用于供用户选择需要查看存量信息的物品;
智能库存管理服务器104还用于,在用户通过所述第一界面选择对应的物品时,展示用户所选择的物品对应的图片以及存量信息;并在用户修改所展示的存量信息时,将该物品对应的存量信息更新。
进一步地,智能库存管理服务器104还用于展示第二界面,第二界面用于供用户选择需要查看实时图像的物品;
智能库存管理服务器104还用于,在用户通过所述第二界面选择对应的物品时,控制智能机器终端101到达该物品所在的位置拍摄并将拍摄到的实时图像上传到智能库存管理服务器104;并将智能库存管理服务器104接收到的实时图像展示。
如图1所示的本申请实施例中的智能库存管理系统,可以包括本申请实施例中的智能机器终端101和智能库存管理服务器104,进一步地,物体识别模块102还用于将物品识别是否成功的反馈信息发送给智能机器终端101;
智能机器终端101还用于,在该反馈信息为识别失败时,从另一角度重新拍摄物品。
进一步地,智能机器终端101用于拍摄物品包括:智能机器终端101定时自主唤醒进行物品拍摄;或者
物品识别模块102还用于向智能机器终端101发送唤醒指令;
智能机器终端101用于拍摄物品包括:智能机器终端101根据接收到的唤醒指令并进行物品拍摄。智能机器终端101具体可以根据接收到的所述物体识别模块102的唤醒指令,唤醒并运动到所述物体识别模块102指定的位置进行物品拍摄。
为了描述的方便,以上所述装置的各部分以功能分为各种模块或单元分别描述。当然,在实施本发明时可以把各模块或单元的功能在同一个或多个软件或硬件中实现。
本领域内的技术人员应明白,本发明的实施例可提供为方法、系统、或计算机程序产品。因此,本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且,本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中
的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品,该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上,使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
尽管已描述了本发明的优选实施例,但本领域内的技术人员一旦得知了基本创造性概念,则可对这些实施例作出另外的变更和修改。所以,所附权利要求意欲解释为包括优选实施例以及落入本发明范围的所有变更和修改。
Claims (24)
- 一种智能库存管理服务器,其特征在于,包括物体识别模块和库存管理模块,其中:所述物体识别模块,用于根据智能机器终端拍摄到的图像识别确定所述图像中的物品及存量;所述库存管理模块,用于将所述物体识别模块识别出的物品及存量信息入库。
- 如权利要求1所述的服务器,其特征在于,所述根据智能机器终端拍摄到的图像识别确定所述图像中的物品及存量包括:利用基于特征提取的机器视觉技术和基于卷积神经网络的深度学习技术进行物体识别。
- 如权利要求1所述的服务器,其特征在于,所述库存管理模块还将所述图像与所述物品及存量信息一起入库。
- 如权利要求3所述的服务器,其特征在于,所述服务器还包括第一交互模块;所述第一交互模块用于展示第一界面,所述第一界面用于供用户选择需要查看存量信息的物品;所述第一交互模块还用于,在用户通过所述第一界面选择对应的物品时,展示用户所选择的物品对应的图片以及存量信息;并在用户修改所展示的存量信息时,将该物品对应的存量信息更新。
- 如权利要求3所述的服务器,其特征在于,所述服务器还包括第二交互模块,所述第一交互模块用于展示第二界面,所述第二界面用于供用户选择需要查看实时图像的物品;所述第二交互模块还用于,在用户通过所述第二界面选择对应的物品时,控制所述智能机器终端到达该物品所在的位置拍摄并将拍摄到的实时图像上传到所述服务器;并将所述服务器接收到的实时图像展示。
- 一种智能库存管理系统,其特征在于,包括权利要求1至5所述的 智能库存管理服务器,以及智能机器终端:所述智能机器终端,用于拍摄物品,并将拍摄到的图像发送到所述服务器。
- 如权利要求6所述的系统,其特征在于,所述物体识别模块还用于将物品识别是否成功的反馈信息发送给所述智能机器终端;所述智能机器终端还用于在所述反馈信息为识别失败时,从另一角度重新拍摄物品。
- 如权利要求6所述的系统,其特征在于,所述智能机器终端用于拍摄物品包括:所述智能机器终端按照预设周期进行物品拍摄;或者,所述物品识别模块还用于向智能机器终端发送唤醒指令;所述智能机器终端用于拍摄物品包括:所述智能机器终端根据接收到的唤醒指令并进行物品拍摄。
- 一种智能机器终端,其特征在于,包括摄像头、第二通信部件、第二处理器部件,其中:所述摄像头,用于拍摄物品;所述第二处理器部件,用于通过所述摄像头拍摄仓库中的物品的图像,并通过所述第二通信部件将拍摄到的图像传送到智能库存管理服务器。
- 如权利要求9所述的智能机器终端,其特征在于,所述第二通信部件还用于接收物品识别是否成功的反馈信息;所述第二处理器部件用于通过所述摄像头拍摄仓库中的物品的图像包括:在所述反馈信息为识别失败时,通过所述摄像头从另一角度重新拍摄物品。
- 如权利要求9所述的智能机器终端,其特征在于,所述第二处理器部件用于通过所述摄像头拍摄仓库中的物品的图像包括:按照预设周期通过所述摄像头拍摄物品;或者在所述第二通信部件接收到唤醒指令时,根据所述指令唤醒智能机器终端并运动到所述唤醒指令指定的位置进行物品拍摄。
- 一种智能库存管理方法,其特征在于,包括:智能机器终端拍摄物品,并将拍摄到的图像发送到智能库存管理服务器;所述智能库存管理服务器接收所述智能机器终端拍摄到的图像,通过对所述智能机器终端拍摄到的图像识别确定所述图像中的物品及存量并保存到库存信息。
- 如权利要求12所述的方法,其特征在于,所述智能库存管理服务器通过对所述智能机器终端拍摄到的图像识别确定所述图像中的物品及存量包括:利用基于特征提取的机器视觉技术和基于卷积神经网络的深度学习技术进行物体识别。
- 如权利要求12所述的方法,其特征在于,所述智能库存管理服务器还将所述图像与所述物品信息一起保存到库存信息。
- 如权利要求14所述的方法,其特征在于,所述服务器还展示第一界面,所述第一界面用于供用户选择需要查看存量信息的物品;所述服务器还在用户通过所述第一界面选择对应的物品时,展示用户所选择的物品对应的图片以及存量信息;并在用户修改所展示的存量信息时,将该物品对应的存量信息更新。
- 如权利要求15所述的方法,其特征在于,所述服务器展示第二界面,所述第二界面用于供用户选择需要查看实时图像的物品;所述服务器还在用户通过所述第二界面选择对应的物品时,控制所述智能机器终端到达该物品所在的位置拍摄并将拍摄到的实时图像上传到服务器;并将服务器接收到的实时图像展示。
- 如权利要求12所述的方法,其特征在于,所述服务器还将物品识别 是否成功的反馈信息发送给所述智能机器终端;所述智能机器终端拍摄物品包括:在所述反馈信息为识别失败时,从另一角度重新拍摄物品。
- 如权利要求12所述的方法,其特征在于,所述智能机器终端拍摄物品包括:所述智能机器终端按照预设周期进行物品拍摄;或者,所述服务器还向所述智能机器终端发送唤醒指令;所述智能机器终端拍摄物品包括:所述智能机器终端根据接收到的唤醒指令并进行物品拍摄。
- 一种智能库存管理的计算机程序产品,所述计算机程序产品包括计算机可读的存储介质和内嵌于其中的计算机程序机制,所述计算机程序机制包括用于执行权利要求12-18中任一所述方法中各个步骤的指令。
- 一种智能库存管理服务器,其特征在于,包括第一通信部件、第一处理器部件和存储器部件,其中:所述第一通信部件,用于接收智能机器终端拍摄到的图像;所述存储器部件,用于存储库存信息;所述第一处理器部件,用于通过对智能机器终端拍摄到的图像识别确定所述图像中的物品及存量,并保存到所述存储器部件。
- 如权利要求20所述的服务器,其特征在于,所述通过对智能机器终端拍摄到的图像识别确定所述图像中的物品及存量包括:利用基于特征提取的机器视觉技术和基于卷积神经网络的深度学习技术进行物体识别。
- 如权利要求20所述的服务器,其特征在于,所述第一处理器部件还将所述图像与所述物品及存量信息一起保存到所述存储器部件。
- 如权利要求22所述的服务器,其特征在于,所述服务器还用于展示第一界面,所述第一界面用于供用户选择需要查看存量信息的物品;所述服务器还用于,在用户通过所述第一界面选择对应的物品时,展 示用户所选择的物品对应的图片以及存量信息;并在用户修改所展示的存量信息时,将该物品对应的存量信息更新。
- 如权利要求22所述的服务器,其特征在于,所述服务器还用于展示第二界面,所述第二界面用于供用户选择需要查看实时图像的物品;所述服务器还用于,在用户通过所述第二界面选择对应的物品时,控制所述智能机器终端到达该物品所在的位置拍摄并将拍摄到的实时图像上传到所述服务器;并将所述服务器接收到的实时图像展示。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2016/100132 WO2018053847A1 (zh) | 2016-09-26 | 2016-09-26 | 一种智能库存管理系统、服务器、方法、终端和程序产品 |
CN201680002680.8A CN107077659A (zh) | 2016-09-26 | 2016-09-26 | 一种智能库存管理系统、服务器、方法、终端和程序产品 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2016/100132 WO2018053847A1 (zh) | 2016-09-26 | 2016-09-26 | 一种智能库存管理系统、服务器、方法、终端和程序产品 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2018053847A1 true WO2018053847A1 (zh) | 2018-03-29 |
Family
ID=59623420
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2016/100132 WO2018053847A1 (zh) | 2016-09-26 | 2016-09-26 | 一种智能库存管理系统、服务器、方法、终端和程序产品 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN107077659A (zh) |
WO (1) | WO2018053847A1 (zh) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108960737A (zh) * | 2018-07-16 | 2018-12-07 | 武汉理工大学 | 基于机器视觉的仓库自动巡检系统及方法 |
CN111343179A (zh) * | 2020-02-25 | 2020-06-26 | 中国工商银行股份有限公司 | 一种链上数据真实性的实时共识方法及装置 |
CN112560537A (zh) * | 2020-12-29 | 2021-03-26 | 云南易见纹语科技有限公司 | 物品纹理处理装置、方法、系统、电子设备及存储介质 |
Families Citing this family (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107705066B (zh) * | 2017-09-15 | 2022-01-07 | 唯品会(海南)电子商务有限公司 | 一种商品入库时信息录入方法及电子设备 |
CN107730168B (zh) * | 2017-09-28 | 2021-10-01 | 中南大学 | 一种基于图像识别的自动售货机自动库存管理系统及方法 |
JP6683666B2 (ja) * | 2017-10-04 | 2020-04-22 | ファナック株式会社 | 識別コード読取装置及び機械学習装置 |
CN109685088A (zh) * | 2017-10-18 | 2019-04-26 | 上海仪电(集团)有限公司中央研究院 | 基于云端分离卷积神经网络的窄带通信智能图像分析系统 |
CN109977975B (zh) * | 2017-12-28 | 2022-11-22 | 沈阳新松机器人自动化股份有限公司 | 物品回收系统和物品回收方法 |
CN111950967A (zh) * | 2018-02-01 | 2020-11-17 | 湖南人文科技学院 | 一种基于热特性图像的库存管理系统 |
CN110119914B (zh) * | 2018-02-06 | 2023-07-25 | 阿里巴巴集团控股有限公司 | 对象补货处理方法、装置和系统 |
CN110119915B (zh) * | 2018-02-06 | 2023-10-13 | 阿里巴巴(中国)网络技术有限公司 | 对象入库处理方法、装置和系统 |
CN109189838A (zh) * | 2018-07-16 | 2019-01-11 | 安徽信尔联信息科技有限公司 | 一种商品整理归类方法 |
CN110765825A (zh) * | 2018-07-27 | 2020-02-07 | 北京京东尚科信息技术有限公司 | 物品摆放状态获取方法和系统 |
CN109118146A (zh) * | 2018-08-28 | 2019-01-01 | 深圳市鼎昇贸易有限公司 | 基于图片识别的库存管理方法及相关产品 |
CN109242085A (zh) * | 2018-08-28 | 2019-01-18 | 深圳市鼎昇贸易有限公司 | 仓库货物电源验证方法及相关产品 |
CN110956422A (zh) * | 2018-09-27 | 2020-04-03 | 上海小蚁科技有限公司 | 商品入库的管理方法、装置及系统、可读存储介质 |
CN109741519B (zh) * | 2018-12-10 | 2021-01-19 | 深圳市思拓通信系统有限公司 | 一种无人超市货架监控系统及其控制方法 |
CN109377289A (zh) * | 2018-12-14 | 2019-02-22 | 深圳码隆科技有限公司 | 销售数据采集方法、装置和服务器 |
CN109886617A (zh) * | 2019-01-11 | 2019-06-14 | 北京明略软件系统有限公司 | 库存管理方法及装置 |
CN109919040B (zh) * | 2019-02-15 | 2022-04-19 | 北京清瞳时代科技有限公司 | 货物的品规信息识别方法及装置 |
CN109902733A (zh) * | 2019-02-22 | 2019-06-18 | 北京三快在线科技有限公司 | 录入物品信息的方法、装置及存储介质 |
CN110175483A (zh) * | 2019-05-16 | 2019-08-27 | 王志伟 | 一种基于标签的识别方法 |
CN110570153A (zh) * | 2019-09-12 | 2019-12-13 | 湖北三六五优米网络有限公司 | 一种基于图片识别技术的自动收货入库系统 |
CN111299161A (zh) * | 2020-02-23 | 2020-06-19 | 安徽古井贡酒股份有限公司 | 自动化分级接酒装置及工艺 |
CN112001228A (zh) * | 2020-07-08 | 2020-11-27 | 上海品览数据科技有限公司 | 一种基于深度学习的视频监控仓库出入库计数系统及方法 |
CN111782104A (zh) * | 2020-07-17 | 2020-10-16 | 汕头市捷优易信息科技有限公司 | 一种图像信息分屏识别显示系统 |
CN112308492A (zh) * | 2020-11-10 | 2021-02-02 | 济南浪潮高新科技投资发展有限公司 | 基于深度学习与知识图谱融合的仓库管理方法及系统 |
CN112884719A (zh) * | 2021-01-29 | 2021-06-01 | 广州富港万嘉智能科技有限公司 | 食材存量盘点方法、可读存储介质以及智能食品机 |
CN114789870A (zh) * | 2022-05-20 | 2022-07-26 | 深圳市信成医疗科技有限公司 | 一种创新型模块化药储仓管理实现模式 |
CN115659452B (zh) * | 2022-09-21 | 2024-04-12 | 联通数字科技有限公司 | 一种智能巡视方法、智能巡视系统及计算机可读存储介质 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101160576A (zh) * | 2005-04-13 | 2008-04-09 | 斯德艾斯有限公司 | 用于测量陈列情况的系统和方法 |
CN102905113A (zh) * | 2012-10-10 | 2013-01-30 | 吉林省粮油科学研究设计院 | 一种基于图像识别技术的粮食仓库智能监控系统 |
CN102915464A (zh) * | 2011-08-02 | 2013-02-06 | 金荣俊 | 利用图像分析的数量判断装置及其方法 |
WO2015136847A1 (ja) * | 2014-03-12 | 2015-09-17 | 日本電気株式会社 | 陳列状況解析装置、陳列状況解析方法およびプログラム記録媒体 |
CN105917371A (zh) * | 2013-11-27 | 2016-08-31 | 松下知识产权经营株式会社 | 商品监控装置、商品监控系统以及商品监控方法 |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE60136352D1 (de) * | 2000-05-23 | 2008-12-11 | Munroe Chirnomas | Verfahren und vorrichtung zur positionierung eines artikelhandhabungsgerätes |
US20140304107A1 (en) * | 2012-12-03 | 2014-10-09 | CLARKE William McALLISTER | Webrooming with rfid-scanning robots |
CN103870943A (zh) * | 2012-12-18 | 2014-06-18 | 郝敬方 | 库存管理系统 |
CN103679430A (zh) * | 2013-12-27 | 2014-03-26 | 钱大宏 | 库存管理方法及用于库存管理的电子货架标签 |
-
2016
- 2016-09-26 WO PCT/CN2016/100132 patent/WO2018053847A1/zh active Application Filing
- 2016-09-26 CN CN201680002680.8A patent/CN107077659A/zh active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101160576A (zh) * | 2005-04-13 | 2008-04-09 | 斯德艾斯有限公司 | 用于测量陈列情况的系统和方法 |
CN102915464A (zh) * | 2011-08-02 | 2013-02-06 | 金荣俊 | 利用图像分析的数量判断装置及其方法 |
CN102905113A (zh) * | 2012-10-10 | 2013-01-30 | 吉林省粮油科学研究设计院 | 一种基于图像识别技术的粮食仓库智能监控系统 |
CN105917371A (zh) * | 2013-11-27 | 2016-08-31 | 松下知识产权经营株式会社 | 商品监控装置、商品监控系统以及商品监控方法 |
WO2015136847A1 (ja) * | 2014-03-12 | 2015-09-17 | 日本電気株式会社 | 陳列状況解析装置、陳列状況解析方法およびプログラム記録媒体 |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108960737A (zh) * | 2018-07-16 | 2018-12-07 | 武汉理工大学 | 基于机器视觉的仓库自动巡检系统及方法 |
CN111343179A (zh) * | 2020-02-25 | 2020-06-26 | 中国工商银行股份有限公司 | 一种链上数据真实性的实时共识方法及装置 |
CN112560537A (zh) * | 2020-12-29 | 2021-03-26 | 云南易见纹语科技有限公司 | 物品纹理处理装置、方法、系统、电子设备及存储介质 |
Also Published As
Publication number | Publication date |
---|---|
CN107077659A (zh) | 2017-08-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2018053847A1 (zh) | 一种智能库存管理系统、服务器、方法、终端和程序产品 | |
US11049278B2 (en) | System and method for visual identification, and system and method for classifying and sorting | |
US9604365B2 (en) | Device and method of transferring articles by using robot | |
WO2019205819A1 (zh) | 即时定位与地图构建方法、计算机设备及存储介质 | |
CN108846449B (zh) | 一种智能设备,商品盘点方法、装置以及设备 | |
US11321966B2 (en) | Method and apparatus for human behavior recognition, and storage medium | |
CN108629284A (zh) | 基于嵌入式视觉系统的实时人脸跟踪和人脸姿态选择的方法及装置 | |
CN105898107B (zh) | 一种目标物体抓拍方法及系统 | |
JP2022542858A (ja) | ディープネットワークの訓練方法 | |
CN109176512A (zh) | 一种体感控制机器人的方法、机器人及控制装置 | |
CN108764391A (zh) | 一种智能设备,商品盘点方法、装置以及设备 | |
CN112262357A (zh) | 针对多个uav的编队确定控制参数 | |
CN112119627A (zh) | 基于云台的目标跟随方法、装置、云台和计算机存储介质 | |
CN109444146A (zh) | 一种工业加工产品的缺陷检测方法、装置及设备 | |
US20240351203A1 (en) | Imaging process for detecting failures modes | |
CN108780319A (zh) | 软件更新方法、系统、移动机器人及服务器 | |
WO2022188410A1 (zh) | 一种基于机械手的设备自动组装控制方法及装置 | |
CN113936340B (zh) | 一种基于训练数据采集的ai模型训练方法及装置 | |
CN112633187B (zh) | 基于图像分析的机器人自动搬运方法、系统和存储介质 | |
CN115648176A (zh) | 视觉引导拾取和放置方法、移动机器人和计算机可读存储介质 | |
US10040195B2 (en) | Recognizing a location of a robot shared in multiple data centers | |
US20230330858A1 (en) | Fine-grained industrial robotic assemblies | |
WO2021233058A1 (zh) | 监控货架上的物品的方法、计算机和系统 | |
CN113807150A (zh) | 数据处理、姿态预测方法、设备及存储介质 | |
US20240212322A1 (en) | Using SLAM 3D Information To Optimize Training And Use Of Deep Neural Networks For Recognition And Tracking Of 3D Object |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 16916586 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC , EPO FORM 1205A DATED 23.09.19. |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 16916586 Country of ref document: EP Kind code of ref document: A1 |